<table border="1" cellspacing="0" cellpadding="8">
    <tr>
        <th>Issue</th>
        <td>
            <a href=https://github.com/llvm/llvm-project/issues/54794>54794</a>
        </td>
    </tr>

    <tr>
        <th>Summary</th>
        <td>
            [AMDGPU][GFX10] Some VOP3 opcodes do not support omod modifier
        </td>
    </tr>

    <tr>
      <th>Labels</th>
      <td>
            backend:AMDGPU
      </td>
    </tr>

    <tr>
      <th>Assignees</th>
      <td>
      </td>
    </tr>

    <tr>
      <th>Reporter</th>
      <td>
          dpreobra
      </td>
    </tr>
</table>

<pre>
    The following GFX10 opcodes do not support output modifier though they should:

    v_div_fixup_f16
    v_fma_f16
    v_max3_f16
    v_med3_f16
    v_min3_f16
    v_interp_p2_f16

An example of failed test:

    v_div_fixup_f16 v5, v1, v2, v3 div:2

Expected result:

    0x05,0x00,0x5f,0xd7,0x01,0x05,0x0e,0x1c

Actual output:

    error: operands are not valid for this GPU or mode

</pre>
<img width="1px" height="1px" alt="" src="http://email.email.llvm.org/o/eJyFU0tv2zAM_jX2hVhgy480Bx-6Ze1pWIE9sFsgS5StTbYEPbL03492srZbOsw2-FEkRX8Uqd7Kx-7ziKCsMfannge4v_tWFmCdsBIDSAuzjRCSc9ZHsCm6FGGyUiuNHuJo0zAS4CME0o3Mqtus2GfFRQI9x4PUx4PSp-QOqmxfOtTE_zZN_FRd2VBe2_R8ZdNzRO8Ojj07zvJ2BjzxyRkEq0BxbVBCxBD_TxeOTcbewbFcJVtlBRRCW9nLve9PDkWkvB5DMq9lLk7FkougWKFRK8jt2Vie4RKCK5TijzJETNxcuvDKD9B768lO7UPPZxmAe1wbeORGS-ry0jId4P7hC5BOfcTz7lx2ldxVO55HHQ12WfP29sOewrJmT_o6FKTCJzshfP34UP1zQijn03zkyZtujNGFhSy7o2_QcUz9RtiJFsYcf8Mb5-13Oj9a6hASBlKaerur87FTitdix0XbMuzbspWiKbeqlI2QfYmqyA3v0YSFdMZYz8UPnJdBvFTAGDHPdccKxoq62JasoncjWavkTdXUu1ZwcVNldYETTcZmobOxfsh9tzLr0xDIaXSI4dnJQ9DDjOtRLfl5osvgO-k82t7zfK2iW0v4BRiGB-Q">